Skip to content

Run mini-swe-agent on ProgramBench!

Choose a tag to compare

View all tags
@klieret klieret released this 21 May 14:37
· 17 commits to main since this release
v2.3.0
adfe202
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

What's Changed

The main feature is compatibility with ProgramBench, a new and ultra-challenging software benchmark.

programbench mini announcement

Fixes

  • fix: add exist_ok=True to mkdir in BubblewrapEnvironment by @hobostay in #802
  • Fix/cost limit zero by @klieret in #825
  • fix: add wall-clock time limit to properly kill agents by @klieret in #832

Full Changelog: v2.2.8...v2.3.0

Contributors

klieret and hobostay
Assets 2
Loading